cowork-hiring-screener

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external resume files (PDF, .docx, text) to perform its core function of scoring and ranking candidates. This creates a surface for indirect prompt injection, where a candidate might embed hidden instructions in their resume to bias the agent's scoring or override its rubric.
  • Ingestion points: External resume files provided in the input folder (SKILL.md).
  • Boundary markers: Absent; the instructions do not implement delimiters or explicit warnings to disregard instructions found within the processed files.
  • Capability inventory: The skill uses Bash, Read, Write, Glob, and Grep for file manipulation and analysis (SKILL.md).
  • Sanitization: Absent; the agent is directed to extract direct quotes and content from resumes without a sanitization or validation layer.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 06:05 PM
Security Audit — agent-trust-hub — cowork-hiring-screener